MuST-Bench
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Style Translation Fidelity Evaluation | MuST-Bench | GPT-4V Fidelity (EN)3.89 | 4 | |
| Stylized Text Generation | MuST-Bench Korean | Style Fidelity40.69 | 4 | |
| Stylized Text Generation | MuST-Bench Chinese | Style Fidelity0.4042 | 4 | |
| Stylized Text Generation | MuST-Bench English | Style Fidelity0.4054 | 4 | |
| Visual Text Generation | MuST-Bench Korean | OCR Accuracy65.77 | 4 | |
| Visual Text Generation | MuST-Bench Chinese | OCR Accuracy74.81 | 4 | |
| Visual Text Generation | MuST-Bench English | OCR Accuracy71.63 | 4 |
Showing 7 of 7 rows